refikcam's picture
First Push
d89cf5e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.9355968236923218,
"min": 1.9355968236923218,
"max": 2.8903281688690186,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 18395.912109375,
"min": 18395.912109375,
"max": 29505.501953125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 6.1082563400268555,
"min": -0.030726147815585136,
"max": 6.1082563400268555,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1191.1099853515625,
"min": -5.960872650146484,
"max": 1191.6982421875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 16.75,
"min": 3.159090909090909,
"max": 16.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 737.0,
"min": 139.0,
"max": 850.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 16.75,
"min": 3.159090909090909,
"max": 16.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 737.0,
"min": 139.0,
"max": 850.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.02948902447387809,
"min": 0.027896860060522274,
"max": 0.038909912247769775,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.02948902447387809,
"min": 0.027896860060522274,
"max": 0.038909912247769775,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3229302113254865,
"min": 0.10911889953745736,
"max": 0.3229302113254865,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3229302113254865,
"min": 0.10911889953745736,
"max": 0.3229302113254865,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.0002836320054559999,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.944099352000012e-06,
"min": 1.944099352000012e-06,
"max": 0.0002836320054559999,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10064800000000002,
"min": 0.10064800000000002,
"max": 0.19454400000000008,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10064800000000002,
"min": 0.10064800000000002,
"max": 0.19454400000000008,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.233520000000021e-05,
"min": 4.233520000000021e-05,
"max": 0.0047277456,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.233520000000021e-05,
"min": 4.233520000000021e-05,
"max": 0.0047277456,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1747778358",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747778738"
},
"total": 380.02307059199995,
"count": 1,
"self": 0.7998792169998978,
"children": {
"run_training.setup": {
"total": 0.0232564090000551,
"count": 1,
"self": 0.0232564090000551
},
"TrainerController.start_learning": {
"total": 379.199934966,
"count": 1,
"self": 0.3381520530031139,
"children": {
"TrainerController._reset_env": {
"total": 3.713655661999951,
"count": 1,
"self": 3.713655661999951
},
"TrainerController.advance": {
"total": 375.02308202199697,
"count": 18192,
"self": 0.35895691799578344,
"children": {
"env_step": {
"total": 291.27460540399795,
"count": 18192,
"self": 221.59184030300207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.47966308599905,
"count": 18192,
"self": 1.2110891979965572,
"children": {
"TorchPolicy.evaluate": {
"total": 68.26857388800249,
"count": 18192,
"self": 68.26857388800249
}
}
},
"workers": {
"total": 0.2031020149968299,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 377.727114274,
"count": 18192,
"is_parallel": true,
"self": 183.01554292100195,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005245630999979767,
"count": 1,
"is_parallel": true,
"self": 0.0037884820000044783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014571489999752885,
"count": 10,
"is_parallel": true,
"self": 0.0014571489999752885
}
}
},
"UnityEnvironment.step": {
"total": 0.059023690000003626,
"count": 1,
"is_parallel": true,
"self": 0.0005907259999275993,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037409499998375395,
"count": 1,
"is_parallel": true,
"self": 0.00037409499998375395
},
"communicator.exchange": {
"total": 0.05620994800005974,
"count": 1,
"is_parallel": true,
"self": 0.05620994800005974
},
"steps_from_proto": {
"total": 0.001848921000032533,
"count": 1,
"is_parallel": true,
"self": 0.0003694399999858433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014794810000466896,
"count": 10,
"is_parallel": true,
"self": 0.0014794810000466896
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 194.71157135299802,
"count": 18191,
"is_parallel": true,
"self": 9.414119472004018,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.352882617991099,
"count": 18191,
"is_parallel": true,
"self": 5.352882617991099
},
"communicator.exchange": {
"total": 149.75771261400394,
"count": 18191,
"is_parallel": true,
"self": 149.75771261400394
},
"steps_from_proto": {
"total": 30.18685664899897,
"count": 18191,
"is_parallel": true,
"self": 5.42034013201237,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.7665165169866,
"count": 181910,
"is_parallel": true,
"self": 24.7665165169866
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 83.38951970000323,
"count": 18192,
"self": 0.4100968340092095,
"children": {
"process_trajectory": {
"total": 25.59871384699386,
"count": 18192,
"self": 25.09244991299363,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5062639340002306,
"count": 4,
"self": 0.5062639340002306
}
}
},
"_update_policy": {
"total": 57.380709019000165,
"count": 19,
"self": 39.57378955899924,
"children": {
"TorchPPOOptimizer.update": {
"total": 17.806919460000927,
"count": 1155,
"self": 17.806919460000927
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1629999789875e-06,
"count": 1,
"self": 1.1629999789875e-06
},
"TrainerController._save_models": {
"total": 0.12504406599998674,
"count": 1,
"self": 0.0011782450000055178,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12386582099998122,
"count": 1,
"self": 0.12386582099998122
}
}
}
}
}
}
}